Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

NeuroBRIDGE: Behavior-Conditioned Koopman Dynamics with Riemannian Alignment for Early Substance Use Initiation Prediction from Longitudinal Functional Connectome

Badhan Mazumder, Sir-Lord Wiafe, Vince D. Calhoun, Dong Hye Ye

Abstract

Early identification of adolescents at risk for substance use initiation (SUI) is vital yet difficult, as most predictors treat connectivity as static or cross-sectional and miss how brain networks change over time and with behavior. We proposed NeuroBRIDGE (Behavior conditioned RIemannian Koopman Dynamics on lonGitudinal connEctomes), a novel graph neural network-based framework that aligns longitudinal functional connectome in a Riemannian tangent space and couples dual-time attention with behavioral-conditioned Koopman dynamics to capture temporal change. Evaluated on ABCD, NeuroBRIDGE improved future SUI prediction over relevant baselines while offering interpretable insights into neural pathways, refining our understanding of neurodevelopmental risk and informing targeted prevention.

NeuroBRIDGE: Behavior-Conditioned Koopman Dynamics with Riemannian Alignment for Early Substance Use Initiation Prediction from Longitudinal Functional Connectome

Abstract

Early identification of adolescents at risk for substance use initiation (SUI) is vital yet difficult, as most predictors treat connectivity as static or cross-sectional and miss how brain networks change over time and with behavior. We proposed NeuroBRIDGE (Behavior conditioned RIemannian Koopman Dynamics on lonGitudinal connEctomes), a novel graph neural network-based framework that aligns longitudinal functional connectome in a Riemannian tangent space and couples dual-time attention with behavioral-conditioned Koopman dynamics to capture temporal change. Evaluated on ABCD, NeuroBRIDGE improved future SUI prediction over relevant baselines while offering interpretable insights into neural pathways, refining our understanding of neurodevelopmental risk and informing targeted prevention.

Paper Structure

This paper contains 15 sections, 7 equations, 2 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Methodology
  3. Geometry-Aware Graph Representation
  4. Riemannian Tangent-Space Embedding
  5. Multi-Scale Heat-Kernel Tokens & Edge-Gated GNN Encoding
  6. Dual Temporal Fusion for Longitudinal Data
  7. Koopman Dynamics with Behavioral Condition
  8. Neural Koopman Operator for Latent Dynamics
  9. Joint Training Objective
  10. Results and Discussion
  11. Dataset and Pre-processing
  12. Experimental Settings
  13. Quantitative Evaluation
  14. Qualitative Evaluation
  15. Conclusions

Figures (2)

  • Figure 1: NeuroBRIDGE overview: Longitudinal rs-fMRIs (Baseline and 2-Year) were processed to generate FNCs $(53\times 53)$ via $NeuroMark$, then SPD-regularized and aligned in a shared Riemannian tangent space to form geometry-aware $k$NN graphs with multi-scale heat-kernel tokens as node features followed by an edge-gated GNN encoding visit-specific embeddings, which are fused by dual-time self/cross attention into a subject-wise vector. A spectrally bounded, CBCL-conditioned Koopman module then models longitudinal change, and employed the predicted–observed year-2 latent to estimate 4-year SUI status, jointly optimized by three different loss terms in an end-to-end manner.
  • Figure 2: Axial view of group-mean, time-mixed edge weights (top $3\%$) for SUI and non-SUI cohorts across the seven networks: cerebellar (CBN), default mode (DMN), cognitive control (CON), visual (VSN), sensorimotor (SMN), auditory (ADN), and subcortical (SCN). Intra-network connections are color-coded by network; cross-network connections are shown in gray. Line width scales with edge weight, emphasizing relatively stronger connections.